© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 9103
    Prev
    Next
    INDEX
    Explanations

    statements indicating certainty or clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìľ¨
    -0.15
    fox
    -0.15
    ala
    -0.14
    彦
    -0.14
    iele
    -0.13
    229
    -0.13
    /in
    -0.13
    ãĤĢ
    -0.13
     (
    -0.13
     slik
    -0.13
    POSITIVE LOGITS
     certain
    0.53
     Certain
    0.48
    Certain
    0.43
     certainty
    0.34
     CERT
    0.31
    ertain
    0.29
     certo
    0.29
     cert
    0.28
     certains
    0.25
     crystal
    0.23
    Activations Density 0.024%

    No Known Activations